ICLR 2026 论文列表

The performance of large language models (LLMs) in program synthesis and mathematical reasoning is fundamentally limited by the quality of their pre-training corpora. We introduce two openly licensed pre-training datasets, released under the Llama 3.3 Community License, that significantly enhance LLM performance by systematically rewriting public data. SwallowCode ($\approx$16.1 billion tokens) refines Python snippets from The-Stack-v2 through a novel four-stage pipeline: syntax validation, pylint-based style filtering, and a two-stage LLM rewriting process that enforces style conformity and transforms snippets into self-contained, algorithmically efficient examples. Unlike prior methods that rely on exclusionary filtering or limited transformations, our transform-and-retain approach refines low-quality code, maximizing data utility. SwallowMath ($\approx$2.3 billion tokens) enhances Finemath-4+ by removing boilerplate, restoring context, and reformatting solutions into concise, step-by-step explanations. Within a fixed 50 billion token training budget, continual pre-training of Llama-3.1-8B with SwallowCode boosts pass@1 by +17.0 on HumanEval and +16.1 on HumanEval+ compared to Stack-Edu, surpassing the baseline model's code generation capabilities. Similarly, substituting SwallowMath yields +12.4 accuracy on GSM8K and +7.6 on MATH. Ablation studies confirm that each pipeline stage contributes incrementally, with rewriting yielding the largest gains. By releasing datasets, prompts, checkpoints, and pipeline code, we ensure reproducibility and provide a transferable transform-and-retain methodology that can be adapted to other base models and LLM rewriting setups.

We study best-of-$N$ for large language models (LLMs) where the selection is based on majority voting. In particular, we analyze the limit $N \to \infty$, which we denote as best-of-$\infty$. While this approach achieves impressive performance in the limit, it requires an infinite test-time budget. To address this, we propose an adaptive generation scheme that selects $N$ based on answer agreement, thereby efficiently allocating inference-time computation. Beyond adaptivity, we extend the framework to weighted ensembles of multiple LLMs, showing that such mixtures can outperform any individual model. The optimal ensemble weighting is formulated and efficiently computed as a mixed-integer linear program. Extensive experiments demonstrate the effectiveness of our approach.

Despite the rapid growth of machine learning research, corresponding code implementations are often unavailable, making it slow and labor-intensive for researchers to reproduce results and build upon prior work. In the meantime, recent Large Language Models (LLMs) excel at understanding scientific documents and generating high-quality code. Inspired by this, we introduce PaperCoder, a multi-agent LLM framework that transforms machine learning papers into operational code repositories. PaperCoder operates in three stages: planning, where it constructs a high-level roadmap, designs the system architecture with diagrams, identifies file dependencies, and generates configuration files; analysis, which focuses on interpreting implementation-specific details; and generation, where modular, dependency-aware code is produced. Moreover, each phase is instantiated through a set of specialized agents designed to collaborate effectively across the pipeline. We then evaluate PaperCoder on generating code implementations from machine learning papers based on both model-based and human evaluations, particularly from the authors of those papers, with author-released repositories as ground truth if available. Our results demonstrate the effectiveness of PaperCoder in creating high-quality, faithful implementations. Furthermore, it consistently shows strengths in the recently released PaperBench benchmark, surpassing strong baselines by substantial margins.

Large Language Models (LLMs) often experience compounding errors during long text generation. Early mistakes can propagate and lead to drift, faulty reasoning, or repetition. While scaling up models improves capabilities, it requires substantial computational resources, and the resulting self-correction behaviour remains unpredictable at inference time. Self-correction is a promising technique for addressing this issue. However, existing approaches have limitations. Supervised training methods can build self-correcting behaviours into models, but require training data collection and lack cross-domain generalizability. Current post-hoc iterative refinement methods operate only at inference time, but must wait for substantial portions of the draft to be generated before providing feedback. This feedback does not guarantee effective guidance, and the same mistake patterns can still reappear. In this paper, we introduce Once-More, a model-agnostic post-hoc self-correction framework that intervenes during generation. Once-More leverages token-level perplexity and feedback from verifiers to provide continuous guided steering of the generation path through a logit redistribution mechanism. This approach essentially helps accumulate "more correct" steps throughout the generation process. Evaluation on multiple benchmarks demonstrates that Once-More achieves state-of-the-art results compared to other self-correction methods. To our knowledge, Once-More is the first post-hoc method to leverage token perplexity and external feedback to perform continuous guided self-correction.

For real-world BCI applications, lightweight Electroencephalography (EEG) systems offer the best cost–deployment balance. However, such spatial sparsity of EEG limits spatial fidelity, hurting learning and introducing bias. EEG spatial super-resolution methods aim to recover high-density EEG signals from sparse measurements, yet is often hindered by distribution shift and signal distortion and thus reducing fidelity and usability for EEG analysis and visualization. To overcome these challenges, we introduce SRGDiff, a step-aware residual-guided diffusion model that formulates EEG spatial super-resolution as dynamic conditional generation. Our key idea is to learn a dynamic residual condition from the low-density input that predicts the step-wise temporal and spatial details to add and uses the evolving cue to steer the denoising process toward high density reconstructions. At each denoising step, the proposed residual condition is additively fused with the previous denoiser feature maps, then a step-dependent affine modulation scales and shifts the activation to produce the current features. This iterative procedure dynamically extracts step-wise temporal rhythms and spatial-topographic cues to steer high-density recovery and maintain a fidelity–consistency balance. We adopt a comprehensive evaluation protocol spanning signal-, feature-, and downstream-level metrics across SEED, SEED-IV, and Localize-MI and multiple upsampling scales. SRGDiff achieves consistent gains of up to 40\% over strong baselines, proving its superiority in the task of EEG spatial super-resolution. Moreover, topographic visualizations comparison and substantial EEG-FID gains jointly indicate that our SR EEG mitigates the spatial–spectral shift between low- and high-density recordings. Our code is available at https://anonymous.4open.science/r/DDPM-VAE-6F6B.

Although continuous-time consistency models (e.g., sCM, MeanFlow) are theoretically principled and empirically powerful for fast academic-scale diffusion, its applicability to large-scale text-to-image and video tasks remains unclear due to infrastructure challenges in Jacobian-vector product (JVP) computation and the limitations of evaluation benchmarks like FID. This work represents the first effort to scale up continuous-time consistency to general application-level image and video diffusion models, and to make JVP-based distillation effective at large scale. We first develop a parallelism-compatible FlashAttention-2 JVP kernel, enabling sCM training on models with over 10 billion parameters and high-dimensional video tasks. Our investigation reveals fundamental quality limitations of sCM in fine-detail generation, which we attribute to error accumulation and the “mode-covering” nature of its forward-divergence objective. To remedy this, we propose the score-regularized continuous-time consistency model (rCM), which incorporates score distillation as a long-skip regularizer. This integration complements sCM with the “mode-seeking” reverse divergence, effectively improving visual quality while maintaining high generation diversity. Validated on large-scale models (Cosmos-Predict2, Wan2.1) up to 14B parameters and 5-second videos, rCM generally matches the state-of-the-art distillation method DMD2 on quality metrics while mitigating mode collapse and offering notable advantages in diversity, all without GAN tuning or extensive hyperparameter searches. The distilled models generate high-fidelity samples in only $1\sim4$ steps, accelerating diffusion sampling by $15\times\sim50\times$. These results position rCM as a practical and theoretically grounded framework for advancing large-scale diffusion distillation. Code is available at https://github.com/NVlabs/rcm.

Autoregressive (AR) models, despite their remarkable successes, encounter limitations in image generation due to sequential prediction of tokens, e.g. local image patches, in a predetermined row-major raster-scan order. Prior works improve AR with various designs of prediction units and orders, however, rely on human inductive biases. This work proposes Basis Autoregressive (BAR), a novel paradigm that conceptualizes tokens as basis vectors within the image space and employs an end-to-end learnable approach to transform basis. By viewing tokens $x_k$ as the projection of image $\mathbf{x}$ onto basis vectors $e_k$, BAR's unified framework refactors fixed token sequences through the linear transform $\mathbf{y}=\mathbf{Ax}$, and encompasses previous methods as specific instances of matrix $\mathbf{A}$. Furthermore, BAR adaptively optimizes the transform matrix with an end-to-end AR objective, thereby discovering effective strategies beyond hand-crafted assumptions. Comprehensive experiments, notably achieving a state-of-the-art FID of 1.15 on the ImageNet-256 benchmark, demonstrate the ability of BAR to overcome human biases and significantly advance image generation, including text-to-image synthesis.

Attribute correlations in the training data will compromise the ability of a deep generative model (DGM) to synthesize images with under-represented attribute combinations ($\textit{i.e.,}$ minority samples). Existing approaches mitigate this by data re-sampling to remove attribute correlations seen by the DGM, using a classifier to provide $\textit{pseudo-supervision}$ for the generation of counterfactual samples, or incorporating inductive bias to explicitly decompose the generation into independent causal mechanisms. We present ProReGen, a $\textit{progressive residual generation}$ approach inspired by the classical Robinson's transformation to partial out from an image attribute $\mathbf{x}_2$ its component $m(\mathbf{x}_1)$ that is predictable by other image attributes $\mathbf{x}_1$, and the residual $\gamma = \mathbf{x}_2 - m(\mathbf{x}_1)$ that is not. This simplifies the original problem of learning a DGM $g(\mathbf{x}_1, \mathbf{x}_2)$ conditioned on correlated inputs, to learning $\tilde{g}(\mathbf{x}_1, \gamma)$ conditioned on orthogonal inputs. It further allows us to progressively learn $\tilde{g}$ by first shifting the burden to abundant majority samples to learn the generator $\tilde{g}(\mathbf{x}_1, \gamma = 0)$, and then expanding it with additional layers $g\_{\text{res}}$ to resolve its difference to $\tilde{g}(\mathbf{x}_1, \gamma)$ using residual attribute $\gamma$ on limited minority samples. On three benchmark datasets with curated varying strengths of attribute correlations, we demonstrate that ProReGen---with input orthogonalizaton and progressive residual learning---improved the correctness and quality of generations compared to existing strategies.

Few-step diffusion or flow-based generative models typically distill a velocity-predicting teacher into a student that predicts a shortcut towards denoised data. This format mismatch has led to complex distillation procedures that often suffer from a quality--diversity trade-off. To address this, we propose policy-based flow models ($\pi$-Flow). $\pi$-Flow modifies the output layer of a student flow model to predict a network-free policy at one timestep. The policy then produces dynamic flow velocities at future substeps with negligible overhead, enabling fast and accurate ODE integration without extra network evaluations. To match the policy's ODE trajectory to the teacher's, we introduce a novel imitation distillation approach, which matches the policy's velocity to the teacher's along the policy's trajectory using a standard $\ell_2$ flow matching loss. By simply mimicking the teacher's behavior, $\pi$-Flow enables stable and scalable training and avoids the quality--diversity trade-off. On ImageNet $256\times 256$, it attains a 1-NFE FID of 2.85, outperforming previous 1-NFE models of the same DiT architecture. On FLUX.1-12B and Qwen-Image-20B at 4 NFEs, $\pi$-Flow achieves substantially better diversity than state-of-the-art DMD models, while maintaining teacher-level quality.

Large Language Models (LLMs) reasoning abilities are increasingly being applied to classical board and card games, but the dominant approach---involving prompting for direct move generation---has significant drawbacks. It relies on the model's implicit fragile pattern-matching capabilities, leading to frequent illegal moves and strategically shallow play. Here we introduce an alternative approach: We use the LLM to translate natural language rules and game trajectories into a formal, executable world model represented as Python code. This generated model---comprising functions for state transition, legal move enumeration, and termination checks---serves as a verifiable simulation engine for high-performance planning algorithms like Monte Carlo tree search (MCTS). In addition, we prompt the LLM to generate heuristic value functions (to make MCTS more efficient), and inference functions (to estimate hidden states in imperfect information games). Our method offers three distinct advantages compared to directly using the LLM as a policy: (1) Verifiability: The generated CWM serves as a formal specification of the game's rules, allowing planners to algorithmically enumerate valid actions and avoid illegal moves, contingent on the correctness of the synthesized model; (2) Strategic Depth: We combine LLM semantic understanding with the deep search power of classical planners; and (3) Generalization: We direct the LLM to focus on the meta-task of data-to-code translation, enabling it to adapt to new games more easily. We evaluate our agent on 10 different games, of which 4 are novel and created for this paper. 5 of the games are fully observed (perfect information), and 5 are partially observed (imperfect information). We find that our method outperforms or matches Gemini 2.5 Pro in 9 out of the 10 considered games.

Alignment training has tradeoffs: it helps language models (LMs) gain in reasoning and instruction following but might lose out on skills such as creativity and calibration, where unaligned base models are better at. We aim to make the best of both worlds through model collaboration, where different models in the training pipeline collaborate and complement each other. Since LM responses feature interleaving skills that favor different models, we propose Switch Generation, where pretrained and aligned model versions take turns to ``speak'' in a response sequence. Specifically, we train a switcher LM by learning from outcomes of choosing different models to generate the next segment across diverse queries and contexts. At inference time, the switcher LM guides different model checkpoints to dynamically generate the next segment where their strengths are most needed. Extensive experiments with 8 model collaboration baselines and 18 datasets show that 1) model collaboration consistently outperforms individual models on 16 out of 18 tasks, and 2) Switch Generation further outperforms baselines by 12.9% on average. Further analysis reveals that Switch Generation discovers compositional skills to solve problems where individual models struggle and generalizes to unseen models and tasks, reusing and repurposing by-products in expensive model training pipelines that are otherwise discarded.

While reinforcement learning (RL) has proven highly effective for general reasoning in vision-language models, its application to tasks requiring deep understanding of information-rich images and structured output generation remains underexplored. Chart-to-code generation exemplifies this challenge, demanding complex reasoning over visual charts to produce structured code. Supervised fine-tuning (SFT) alone is often insufficient, highlighting the need for effective RL strategies tailored to structured outputs. In this paper, we systematically investigate the performance plateau of SFT through large-scale experiments and propose Multimodal Structured Reinforcement Learning (MSRL) for chart-to-code generation. We construct the largest training corpus to date, with 3 million chart-code pairs curated from real-world tables in arXiv papers, addressing the limitations of previous synthetic datasets. Despite achieving state-of-the-art performance, our experiments show that simply increasing SFT data eventually leads to diminishing improvements. To break this plateau, MSRL employs a multi-granularity reward system that integrates both textual and visual feedback. At the textual level, rule-based rewards validate fine-grained code details, while at the visual level, a model-based reward assesses the structural similarity between rendered code and ground-truth charts. We implement a two-stage curriculum training strategy, first optimizing the model with textual rewards and then incorporating visual signals for further enhancement. Experimental results demonstrate that MSRL substantially breaks the SFT plateau, improving high-level metrics by 6.2% and 9.9% on ChartMimic and ReachQA benchmarks, respectively. Notably, our method outperforms all existing approaches in the chart domain and achieves competitive results with advanced closed-source models.

Large language models (LLMs) are increasingly integrated in software development, but ensuring correctness in LLM-generated code remains challenging and often requires costly manual review. Verifiable code generation---jointly generating code, specifications, and proofs of code-specification alignment---offers a promising path to address this limitation and further unleash LLMs' benefits in coding. Yet, there exists a significant gap in evaluation: current benchmarks often focus on only individual components rather than providing a holistic evaluation framework of all tasks. In this paper, we introduce VERINA (Verifiable Code Generation Arena), a high-quality benchmark enabling a comprehensive and modular evaluation of code, specification, and proof generation as well as their compositions. VERINA consists of 189 manually curated coding tasks in Lean, with detailed problem descriptions, reference implementations, formal specifications, and extensive test suites. Our extensive evaluation of state-of-the-art LLMs reveals significant challenges in verifiable code generation, especially in proof generation, underscoring the need for improving LLM-based theorem provers in verification domains. The best model, OpenAI o3, achieves a 72.6% code correctness rate, 52.3% for specification soundness and completeness, and a mere 4.9% proof success rate (based on one trial per task). We hope VERINA will catalyze progress in verifiable code generation by providing a rigorous and comprehensive benchmark.

Large Language Models (LLMs) are improving at an exceptional rate. With the advent of agentic workflows, multi-turn dialogue has become the de facto mode of interaction with LLMs for completing long and complex tasks. While LLM capabilities continue to improve, they remain increasingly susceptible to jailbreaking, especially in multi-turn scenarios where harmful intent can be subtly injected across the conversation to produce nefarious outcomes. While single-turn attacks have been extensively explored, adaptability, efficiency and effectiveness continue to remain key challenges for their multi-turn counterparts. To address these gaps, we present PLAGUE, a novel plug-and-play framework for designing multi-turn attacks inspired by lifelong-learning agents. PLAGUE dissects the lifetime of a multi-turn attack into three carefully designed phases (Primer, Planner and Finisher) that enable a systematic and information-rich exploration of the multi-turn attack family. Evaluations show that red-teaming agents designed using PLAGUE achieve state-of-the-art jailbreaking results, improving attack success rates (ASR) by more than 30% across leading models in a lesser or comparable query budget. Particularly, PLAGUE enables an ASR (based on StrongReject) of 81.4% on OpenAI's o3 and 67.3% on Claude's Opus 4.1, two models that are considered highly resistant to jailbreaks in safety literature. Our work offers tools and insights to understand the importance of plan initialization, context optimization, and lifelong learning in crafting multi-turn attacks for a comprehensive model vulnerability evaluation.

Although large language models (LLMs) have achieved remarkable success across various domains, their considerable scale necessitates substantial computational resources, posing significant challenges for deployment in resource-constrained environments. Layer pruning, as a simple yet effective compression method, removes layers of a model directly, reducing computational overhead. However, what are the best practices for layer pruning in LLMs? Are sophisticated layer selection metrics truly effective? Does the LoRA (Low-Rank Approximation) family, widely regarded as a leading method for pruned model fine-tuning, truly meet expectations when applied to post-pruning fine-tuning? To answer these questions, we dedicate thousands of GPU hours to benchmarking layer pruning in LLMs and gaining insights across multiple dimensions. Our results demonstrate that a simple approach, i.e., pruning the final layers followed by fine-tuning the lm\_head and the remaining last three layers, yields remarkably strong performance. These pruning strategies are further supported by theoretical analyses based on the gradient flow. Following this guide, our method surpasses existing state-of-the-art pruning methods by $5.62\%$–$17.27\%$ on Llama-3.1-8B-It, by $2.36\%$–$19.45\%$ on Llama-3-8B and by $4.34\%$–$9.59\%$ on Llama-3-70B. The code is available at at https://github.com/yaolu-zjut/Navigation_LLM_layer_pruning.

方向：知识密集型生成 + 结构化检索 解决 RAG 中检索上下文非结构化导致多步推理困难的问题，提出检索并结构化的方法。

交互式定理证明器（ ITP ）需要手动形式化，这是劳动密集型的，需要专业知识。虽然自动化形式化提供了一种潜在的解决方案，但它面临两大挑战：模型幻觉（例如，未定义的谓词、符号滥用和版本不兼容）以及自然语言描述中模糊或缺少前提导致的语义差距。 为了解决这些问题，我们提出了CRAMF ，这是一个概念驱动的检索增强数学形式化框架。CRAMF通过检索核心数学概念的正式定义来增强基于LLM的自形式化，在代码生成期间提供上下文基础。 然而，由于缺乏结构化知识库，数学概念的多态性以及形式检索所需的高精度，在此环境中应用检索增强生成（ RAG ）并非易事。 我们引入了一个用于从Mathlib4自动构建概念定义知识库的框架， Mathlib4是精益4定理证明器的标准数学库，索引了26,000多个形式定义和1,000多个核心数学概念。为了解决概念多态性，我们提出了使用域级和应用级信号的上下文查询增强。 此外，我们设计了一种具有重新排序的双通道混合检索策略，以确保准确和相关的定义检索。在miniF2F、ProofNet和我们新提出的AdvancedMath基准上的实验表明， CRAMF可以无缝集成到基于LLM的自动形式化器中，从而在翻译准确性方面实现了一致的提高，最高可达62.1% ，平均相对提高29.9%。

检索增强生成（ RAG ）被广泛用于通过利用外部知识来减轻大型语言模型（ LLM ）的幻觉。传统的RAG系统虽然对简单的查询有效，但却与信息分散的大规模非结构化语料库作斗争。最近的进步结合了知识图来捕获关系结构，从而为复杂的多跳推理任务实现更全面的检索。 然而，现有的基于图的RAG （ GraphRAG ）方法依赖于不稳定且昂贵的关系提取来构建图，通常会产生具有不正确或不一致关系的噪声图，从而降低检索质量。 在本文中，我们重新审视了现有GraphRAG系统的管道，并提出了基于线性图的检索增强生成（ LinearRAG ） ，这是一个实现可靠图构建和精确通道检索的高效框架。具体来说， LinearRAG构建了一个无关系的层次图，称为Tri-Graph ，仅使用轻量级实体提取和语义链接，避免了不稳定的关系建模。 这种新的图形构建范式与语料库大小线性扩展，无需额外的代币消耗，为原始通道提供了经济可靠的索引。对于检索， LinearRAG采用两阶段策略： （ i ）通过局部语义桥接激活相关实体，然后（ ii ）通过全局重要性聚合进行通道检索。 在四个基准数据集上的广泛实验表明， LinearRAG显著优于基线模型。我们的代码和数据集可在https://github.com/DEEP-PolyU/LinearRAG上获得。

尽管最近取得了进展，但大型语言模型（ LLM ）仍然会生成易受攻击的代码。检索增强生成（ RAG ）具有通过整合外部安全知识来增强LLM以实现安全代码生成的潜力。然而，传统的RAG设计难以应对原始安全相关文档的噪音，现有的检索方法忽略了任务描述中隐含的重要安全语义。 为了解决这些问题，我们提出了\ textsc {Rescue} ，这是一个新的RAG框架，用于安全代码生成，具有两项关键创新。首先，我们提出了一种混合知识库构建方法，该方法将LLM辅助的集群-然后-总结蒸馏与程序切片相结合，生成高级安全指南和简洁的、以安全为中心的代码示例。 其次，我们设计了一个层次化的多方面检索，从上到下遍历构建的知识库，并在每个层次上集成多个安全关键事实，确保全面准确的检索。我们在四个基准上评估了\ textsc {Rescue} ，并将其与六个LLM的五种最先进的安全代码生成方法进行了比较。 结果表明，\ textsc {Rescue}将SecurePass @ 1指标平均提高了4.8分，从而建立了全新的最先进的安全性能。此外，我们进行了深入的分析和消融研究，以严格验证\ textsc {Rescue}中单个组件的有效性。我们的代码位于\ url {https://github.com/steven1518/RESCUE}。